Detecting sleep using heart rate and motion data from multisensor consumer-grade wearables, relative to wrist actigraphy and polysomnography

Real-World Accuracy of Wearable Activity Trackers for Detecting Medical Conditions: Systematic Review and Meta-Analysis

BACKGROUND

Wearable activity trackers, including fitness bands and smartwatches, offer the potential for disease detection by monitoring physiological parameters. However, their accuracy as specific disease diagnostic tools remains uncertain.

OBJECTIVE

This systematic review and meta-analysis aims to evaluate whether wearable activity trackers can be used to detect disease and medical events.

METHODS

Ten electronic databases were searched for studies published from inception to April 1, 2023. Studies were eligible if they used a wearable activity tracker to diagnose or detect a medical condition or event (eg, falls) in free-living conditions in adults. Meta-analyses were performed to assess the overall area under the curve (%), accuracy (%), sensitivity (%), specificity (%), and positive predictive value (%). Subgroup analyses were performed to assess device type (Fitbit, Oura ring, and mixed). The risk of bias was assessed using the Joanna Briggs Institute Critical Appraisal Checklist for Diagnostic Test Accuracy Studies.

RESULTS

A total of 28 studies were included, involving a total of 1,226,801 participants (age range 28.6-78.3). In total, 16 (57%) studies used wearables for diagnosis of COVID-19, 5 (18%) studies for atrial fibrillation, 3 (11%) studies for arrhythmia or abnormal pulse, 3 (11%) studies for falls, and 1 (4%) study for viral symptoms. The devices used were Fitbit (n=6), Apple watch (n=6), Oura ring (n=3), a combination of devices (n=7), Empatica E4 (n=1), Dynaport MoveMonitor (n=2), Samsung Galaxy Watch (n=1), and other or not specified (n=2). For COVID-19 detection, meta-analyses showed a pooled area under the curve of 80.2% (95% CI 71.0%-89.3%), an accuracy of 87.5% (95% CI 81.6%-93.5%), a sensitivity of 79.5% (95% CI 67.7%-91.3%), and specificity of 76.8% (95% CI 69.4%-84.1%). For atrial fibrillation detection, pooled positive predictive value was 87.4% (95% CI 75.7%-99.1%), sensitivity was 94.2% (95% CI 88.7%-99.7%), and specificity was 95.3% (95% CI 91.8%-98.8%). For fall detection, pooled sensitivity was 81.9% (95% CI 75.1%-88.1%) and specificity was 62.5% (95% CI 14.4%-100%).

CONCLUSIONS

Wearable activity trackers show promise in disease detection, with notable accuracy in identifying atrial fibrillation and COVID-19. While these findings are encouraging, further research and improvements are required to enhance their diagnostic precision and applicability.

TRIAL REGISTRATION

Prospero CRD42023407867; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=407867.

Enhancing Spinal Cord Injury Care: Using Wearable Technologies for Physical Activity, Sleep, and Cardiovascular Health

Wearable devices have the potential to advance health care by enabling real-time monitoring of biobehavioral data and facilitating the management of an individual's health conditions. Individuals living with spinal cord injury (SCI) have impaired motor function, which results in deconditioning and worsening cardiovascular health outcomes. Wearable devices may promote physical activity and allow the monitoring of secondary complications associated with SCI, potentially improving motor function, sleep, and cardiovascular health. However, several challenges remain to optimize the application of wearable technologies within this population. One is striking a balance between research-grade and consumer-grade devices in terms of cost, accessibility, and validity. Additionally, limited literature supports the validity and use of wearable technology in monitoring cardio-autonomic and sleep outcomes for individuals with SCI. Future directions include conducting performance evaluations of wearable devices to precisely capture the additional variation in movement and physiological parameters seen in those with SCI. Moreover, efforts to make the devices small, lightweight, and inexpensive for consumer ease of use may affect those with severe motor impairments. Overcoming these challenges holds the potential for wearable devices to help individuals living with SCI receive timely feedback to manage their health conditions and help clinicians gather comprehensive patient health information to aid in diagnosis and treatment.

Predicting daily recovery during long-term endurance training using machine learning analysis

PURPOSE

The aim of this study was to determine if machine learning models could predict the perceived morning recovery status (AM PRS) and daily change in heart rate variability (HRV change) of endurance athletes based on training, dietary intake, sleep, HRV, and subjective well-being measures.

METHODS

Self-selected nutrition intake, exercise training, sleep habits, HRV, and subjective well-being of 43 endurance athletes ranging from professional to recreationally trained were monitored daily for 12 weeks (3572 days of tracking). Global and individualized models were constructed using machine learning techniques, with the single best algorithm chosen for each model. The model performance was compared with a baseline intercept-only model.

RESULTS

Prediction error (root mean square error [RMSE]) was lower than baseline for the group models (11.8 vs. 14.1 and 0.22 vs. 0.29 for AM PRS and HRV change, respectively). At the individual level, prediction accuracy outperformed the baseline model but varied greatly across participants (RMSE range 5.5-23.6 and 0.05-0.44 for AM PRS and HRV change, respectively).

CONCLUSION

At the group level, daily recovery measures can be predicted based on commonly measured variables, with a small subset of variables providing most of the predictive power. However, at the individual level, the key variables may vary, and additional data may be needed to improve the prediction accuracy.

State of the science and recommendations for using wearable technology in sleep and circadian research

Wearable sleep-tracking technology is of growing use in the sleep and circadian fields, including for applications across other disciplines, inclusive of a variety of disease states. Patients increasingly present sleep data derived from their wearable devices to their providers and the ever-increasing availability of commercial devices and new-generation research/clinical tools has led to the wide adoption of wearables in research, which has become even more relevant given the discontinuation of the Philips Respironics Actiwatch. Standards for evaluating the performance of wearable sleep-tracking devices have been introduced and the available evidence suggests that consumer-grade devices exceed the performance of traditional actigraphy in assessing sleep as defined by polysomnogram. However, clear limitations exist, for example, the misclassification of wakefulness during the sleep period, problems with sleep tracking outside of the main sleep bout or nighttime period, artifacts, and unclear translation of performance to individuals with certain characteristics or comorbidities. This is of particular relevance when person-specific factors (like skin color or obesity) negatively impact sensor performance with the potential downstream impact of augmenting already existing healthcare disparities. However, wearable sleep-tracking technology holds great promise for our field, given features distinct from traditional actigraphy such as measurement of autonomic parameters, estimation of circadian features, and the potential to integrate other self-reported, objective, and passively recorded health indicators. Scientists face numerous decision points and barriers when incorporating traditional actigraphy, consumer-grade multi-sensor devices, or contemporary research/clinical-grade sleep trackers into their research. Considerations include wearable device capabilities and performance, target population and goals of the study, wearable device outputs and availability of raw and aggregate data, and data extraction, processing, and analysis. Given the difficulties in the implementation and utilization of wearable sleep-tracking technology in real-world research and clinical settings, the following State of the Science review requested by the Sleep Research Society aims to address the following questions. What data can wearable sleep-tracking devices provide? How accurate are these data? What should be taken into account when incorporating wearable sleep-tracking devices into research? These outstanding questions and surrounding considerations motivated this work, outlining practical recommendations for using wearable technology in sleep and circadian research.

Performance Evaluation of a New Sport Watch in Sleep Tracking: A Comparison against Overnight Polysomnography in Young Adults

Introduction: This study aimed to validate the ability of a prototype sport watch (Polar Electro Oy, FI) to recognize wake and sleep states in two trials with and without an interval training session (IT) 6 h prior to bedtime. Methods: Thirty-six participants completed this study. Participants performed a maximal aerobic test and three polysomnography (PSG) assessments. The first night served as a device familiarization night and to screen for sleep apnea. The second and third in-home PSG assessments were counterbalanced with/without IT. Accuracy and agreement in detecting sleep stages were calculated between PSG and the prototype. Results: Accuracy for the different sleep stages (REM, N1 and N2, N3, and awake) as a true positive for the nights without exercise was 84 ± 5%, 64 ± 6%, 81 ± 6%, and 91 ± 6%, respectively, and for the nights with exercise was 83 ± 7%, 63 ± 8%, 80 ± 7%, and 92 ± 6%, respectively. The agreement for the sleep night without exercise was 60.1 ± 8.1%, k = 0.39 ± 0.1, and with exercise was 59.2 ± 9.8%, k = 0.36 ± 0.1. No significant differences were observed between nights or between the sexes. Conclusion: The prototype showed better or similar accuracy and agreement to wrist-worn consumer products on the market for the detection of sleep stages with healthy adults. However, further investigations will need to be conducted with other populations.

Evaluating reliability in wearable devices for sleep staging

Sleep is crucial for physical and mental health, but traditional sleep quality assessment methods have limitations. This scoping review analyzes 35 articles from the past decade, evaluating 62 wearable setups with varying sensors, algorithms, and features. Our analysis indicates a trend towards combining accelerometer and photoplethysmography (PPG) data for out-of-lab sleep staging. Devices using only accelerometer data are effective for sleep/wake detection but fall short in identifying multiple sleep stages, unlike those incorporating PPG signals. To enhance the reliability of sleep staging wearables, we propose five recommendations: (1) Algorithm validation with equity, diversity, and inclusion considerations, (2) Comparative performance analysis of commercial algorithms across multiple sleep stages, (3) Exploration of feature impacts on algorithm accuracy, (4) Consistent reporting of performance metrics for objective reliability assessment, and (5) Encouragement of open-source classifier and data availability. Implementing these recommendations can improve the accuracy and reliability of sleep staging algorithms in wearables, solidifying their value in research and clinical settings.

Validity and reliability of the Oura Ring Generation 3 (Gen3) with Oura sleep staging algorithm 2.0 (OSSA 2.0) when compared to multi-night ambulatory polysomnography: A validation study of 96 participants and 421,045 epochs

PURPOSE

To evaluate the validity and the reliability of the Oura Ring Generation 3 (Gen3) with Oura Sleep Staging Algorithm 2.0 (OSSA 2.0) through multi-night polysomnography (PSG).

PARTICIPANTS AND METHODS

Participants were 96 generally healthy Japanese men and women aged between 20 and 70 years contributing with 421,045 30-s epochs. Sleep scoring was performed according to American Academy of Sleep Medicine criteria. Each participant could contribute with a maximum of three polysomnography (PSG) nights. Within-participant means were created for each sleep measure and paired t-tests were used to compare equivalent measures obtained from the PSG and Oura Rings (non-dominant and dominant hand). Agreement between sleep measures were assessed using Bland-Altman plots. Interrater reliability for epoch accuracy was determined by prevalence-adjusted and bias-adjusted kappa (PABAK).

RESULTS

The Oura Ring did not significantly differ from PSG for the measures time in bed, total sleep time, sleep onset latency, sleep period time, wake after sleep onset, time spent in light sleep, and time spent in deep sleep. Oura Rings worn on the non-dominant- and dominant-hand underestimated sleep efficiency by 1.1 %-1.5 % and time spent in REM sleep by 4.1-5.6 min. The Oura Ring had a sensitivity of 94.4 %-94.5 %, specificity of 73.0 %-74.6 %, a predictive value for sleep of 95.9 %-96.1 %, a predictive value for wake of 66.6 %-67.0 %, and accuracy of 91.7 %-91.8 %. PABAK was 0.83-0.84 and reliability was 94.8 %. Sleep staging accuracy ranged between 75.5 % (light sleep) and 90.6 % (REM sleep).

CONCLUSIONS

The Oura Ring Gen3 with OSSA 2.0 shows good agreement with PSG for global sleep measures and time spent in light and deep sleep.

Effects of Temperature, Duration, and Heating Height of Foot Thermal Therapy on Sleep Quality of Older Adults: A Systematic Review and Meta-Analysis

Background: Sleep disturbances, which are common problems in older adults, often lead to cognitive decline and depression and may even increase mortality risk. Foot thermal therapy is a simple and safe approach for improving sleep and is associated with relatively few side effects. However, the effect of different operations of foot thermal therapy on sleep quality in older adults is inconclusive. This study aimed to access the effects of temperature, duration, and heating height of foot thermal therapy (administered through a footbath) on the subjective and objective sleep quality of older adults. Methods: Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guideline, eight databases were searched for all relevant articles published up to July 2023, and a rigorous systematic review and meta-analysis was conducted. This study was registered in the PROSPERO database (CRD42022383460). Inclusion criteria were: (1) participants with a mean age ≥60 years; (2) interventions that included foot thermal therapy; (3) a control group that received routine care but no thermal therapy; (4) outcome measurements that assessed sleep quality; and (5) the studies that utilized randomized controlled trials or quasi-experimental studies. Methodological quality was assessed using the Joanna Briggs Institute critical appraisal tools. The meta-analysis was performed using RevMan version 5.4. Results: A total of 11 studies were included. Foot thermal therapy before bedtime improved subjective sleep quality in older adults, with optimal parameters of 40°C temperature (standardized mean difference [SMD] = 0.66, 95% confidence interval [CI]: 0.33 to 0.99), ≤20-min duration (SMD = 0.66, 95% CI: 0.39 to 0.93), and 10 cm heating height (SMD = 0.78, 95% CI: 0.45 to 1.11). Subgroup analyses revealed that a temperature of 41°C-42°C can improve objective sleep latency (SMD = 0.54, 95% CI: 0.09 to 0.99). Conclusions: It is recommended to administer foot thermal therapy (40°C; ≤20 min; 10 cm above the ankle) to older adults 1 h before their bedtime. If they have trouble falling asleep, the temperature can be increased to 41°C-42°C.

Objectively measured peri-vaccination sleep does not predict COVID-19 breakthrough infection

Prior studies have shown that sleep duration peri-vaccination influences an individual's antibody response. However, whether peri-vaccination sleep affects real-world vaccine effectiveness is unknown. Here, we tested whether objectively measured sleep around COVID-19 vaccination affected breakthrough infection rates. DETECT is a study of digitally recruited participants who report COVID-19-related information, including vaccination and illness data. Objective sleep data are also recorded through activity trackers. We compared the impact of sleep duration, sleep efficiency, and frequency of awakenings on reported breakthrough infection after the 2nd vaccination and 1st COVID-19 booster. Logistic regression models were created to examine if sleep metrics predicted COVID-19 breakthrough infection independent of age and gender. Self-reported breakthrough COVID-19 infection following 2nd COVID-19 vaccination and 1st booster. 256 out of 5265 individuals reported a breakthrough infection after the 2nd vaccine, and 581 out of 2583 individuals reported a breakthrough after the 1st booster. There was no difference in sleep duration between those with and without breakthrough infection. Increased awakening frequency was associated with breakthrough infection after the 1st booster with 3.01 ± 0.65 awakenings/hour in the breakthrough group compared to 2.82 ± 0.65 awakenings/hour in those without breakthrough (P < 0.001). Cox proportional hazards modeling showed that age < 60 years (hazard ratio 2.15, P < 0.001) and frequency of awakenings (hazard ratio 1.17, P = 0.019) were associated with breakthrough infection after the 1st booster. Sleep duration was not associated with breakthrough infection after COVID vaccination. While increased awakening frequency during sleep was associated with breakthrough infection beyond traditional risk factors, the clinical implications of this finding are unclear.

Selecting a sleep tracker from EEG-based, iteratively improved, low-cost multisensor, and actigraphy-only devices

AIMS

Evaluate the performance of 6 wearable sleep trackers across 4 classes (EEG-based headband, research-grade actigraphy, iteratively improved consumer tracker, low-cost consumer tracker).

FOCUS TECHNOLOGY

Dreem 3 headband, Actigraph GT9X, Oura Ring Gen3, Fitbit Sense, Xiaomi Mi Band 7, Axtro Fit3.

REFERENCE TECHNOLOGY

In-lab polysomnography with 3-reader, consensus sleep scoring.

SAMPLE

Sixty participants (26 males) across 3 age groups (18-30, 31-50, and 51-70years).

DESIGN

Overnight in a sleep laboratory from habitual sleep time to wake time.

CORE ANALYTICS

Discrepancy and epoch-by-epoch analyses for sleep/wake (2-stage) and sleep-stage (4-stage; wake/light/deep/rapid eye movement) classification (devices vs. polysomnography).

CORE OUTCOMES

EEG-based Dreem performed the best (2-stage kappa=0.76, 4-stage kappa=0.76-0.86) with the lowest total sleep time, sleep efficiency, sleep onset latency, and wake after sleep onset discrepancies vs. polysomnography. This was followed by the iteratively improved consumer trackers: Oura (2-stage kappa=0.64, 4-stage kappa=0.55-0.70) and Fitbit (2-stage kappa=0.58, 4-stage kappa=0.45-0.60) which had comparable total sleep time and sleep efficiency discrepancies that outperformed accelerometry-only Actigraph (2-stage kappa=0.47). The low-cost consumer trackers had poorest overall performance (2-stage kappa<0.31, 4-stage kappa<0.33).

IMPORTANT ADDITIONAL OUTCOMES

Proportional biases were driven by nights with poorer sleep (longer sleep onset latencies and/or wake after sleep onset).

CORE CONCLUSION

EEG-based Dreem is recommended when evaluating poor quality sleep or when highest accuracy sleep-staging is required. Iteratively improved non-EEG sleep trackers (Oura, Fitbit) balance classification accuracy with well-tolerated, and economic deployment at-scale, and are recommended for studies involving mostly healthy sleepers. The low-cost trackers, can log time in bed but are not recommended for research use.

Imputing missing sleep data from wearables with neural networks in real-world settings

Sleep is a critical component of health and well-being but collecting and analyzing accurate longitudinal sleep data can be challenging, especially outside of laboratory settings. We propose a simple neural network model titled SOMNI (Sleep data restOration using Machine learning and Non-negative matrix factorIzation [NMF]) for imputing missing rest-activity data from actigraphy, which can enable clinicians to better handle missing data and monitor sleep-wake cycles of individuals with highly irregular sleep-wake patterns. The model consists of two hidden layers and uses NMF to capture hidden longitudinal sleep-wake patterns of individuals with disturbed sleep-wake cycles. Based on this, we develop two approaches: the individual approach imputes missing data based on the data from only one participant, while the global approach imputes missing data based on the data across multiple participants. Our models are tested with shift and non-shift workers' data from three independent hospitals. Both approaches can accurately impute missing data up to 24 hours of long dataset (>50 days) even for shift workers with extremely irregular sleep-wake patterns (AUC > 0.86). On the other hand, for short dataset (~15 days), only the global model is accurate (AUC > 0.77). Our approach can be used to help clinicians monitor sleep-wake cycles of patients with sleep disorders outside of laboratory settings without relying on sleep diaries, ultimately improving sleep health outcomes.

To be or not to be hallucinating: Implications of hypnagogic/hypnopompic experiences and lucid dreaming for brain disorders

The boundaries between waking and sleeping-when falling asleep (hypnagogic) or waking up (hypnopompic)-can be challenging for our ability to monitor and interpret reality. Without proper understanding, bizarre but relatively normal hypnagogic/hypnopompic experiences can be misinterpreted as psychotic hallucinations (occurring, by definition, in the fully awake state), potentially leading to stigma and misdiagnosis in clinical contexts and to misconception and bias in research contexts. This Perspective proposes that conceptual and practical understanding for differentiating hallucinations from hypnagogic/hypnopompic experiences may be offered by lucid dreaming, the state in which one is aware of dreaming while sleeping. I first introduce a possible systematization of the phenomenological range of hypnagogic/hypnopompic experiences that can occur in the transition from awake to REM dreaming (including hypnagogic perceptions, transition symptoms, sleep paralysis, false awakenings, and out-of-body experiences). I then outline how metacognitive strategies used by lucid dreamers to gain/confirm oneiric lucidity could be tested for better differentiating hypnagogic/hypnopompic experiences from hallucinations. The relevance of hypnagogic/hypnopompic experiences and lucid dreaming is analyzed for schizophrenia and narcolepsy, and discussed for neurodegenerative diseases, particularly Lewy-body disorders (i.e. Parkinson's disease, Parkinson's disease dementia, and dementia with Lewy bodies), offering testable hypotheses for empirical investigation. Finally, emotionally positive lucid dreams triggered or enhanced by training/induction strategies or by a pathological process may have intrinsic therapeutic value if properly recognized and guided. The overall intention is to raise awareness and foster further research about the possible diagnostic, prognostic, and therapeutic implications of hypnagogic/hypnopompic experiences and lucid dreaming for brain disorders.

Scanning of obstructive sleep apnea syndrome using smartwatch: A comparison of smartwatch and polysomnography

BACKGROUND

Obstructive Sleep Apnea Syndrome (OSAS), which significantly impairs nighttime sleep quality and causes excessive daytime sleepiness, not only reduces the quality of life of patients, but also increases the social and socioeconomic burden. Wearable-noninvasive devices can provide faster OSAS screening and follow-up. Smartwatches as an objective, non-invasive, practical and relatively inexpensive method, they are attractive candidates for pre-evaluation of OSAS and referral to a physician. In this study, it was aimed to evaluate the effectiveness of a smart watch in detecting OSAS findings compared to the gold standard polysomnograhy (PSG).

METHODS

PSG data of the study group were compared with data such as SpO2, heart rate and saturation obtained by smartwatch from both sides, and the Cohen's kappa was used to measure for two methods and predictive values were evaluated.

RESULTS

A total of 115 participants [44 female (38.3%), mean age (SD): 49.24 (11.39)] were enrolled. 75 (65.22%) of the participants were diagnosed with OSAS, of which 29 (25.22%) participants have severe OSAS. The smartwatch showed good sensitivity (75% to 96%), specificity (79% to 91%), and diagnostic accuracy (AUC: 0.84 to 0.93) in predicting apnea and severe apnea, respectively. The highest agreement between PSG and smartwatch and the diagnostic ability of smartwatch were found in persons with severe OSAS.

CONCLUSION

The high PPV-NPV values in our study and the good compatibility coefficient of the smart watch with the PSG device can contribute to the expansion of the usage areas of smart watches that come into the lives of many people in daily practice.

Exploring Variations in Sleep Perception: Comparative Study of Chatbot Sleep Logs and Fitbit Sleep Data

BACKGROUND

Patient-generated health data are important in the management of several diseases. Although there are limitations, information can be obtained using a wearable device and time-related information such as exercise time or sleep time can also be obtained. Fitbits can be used to acquire sleep onset, sleep offset, total sleep time (TST), and wakefulness after sleep onset (WASO) data, although there are limitations regarding the depth of sleep and satisfaction; therefore, the patient's subjective response is still important information that cannot be replaced by wearable devices.

OBJECTIVE

To effectively use patient-generated health data related to time such as sleep, it is first necessary to understand the characteristics of the time response recorded by the user. Therefore, the aim of this study was to analyze the characteristics of individuals' time perception in comparison with wearable data.

METHODS

Sleep data were acquired for 2 weeks using a Fitbit. Participants' sleep records were collected daily through chatbot conversations while wearing the Fitbit, and the two sets of data were statistically compared.

RESULTS

In total, 736 people aged 30-59 years were recruited for this study, and the sleep data of 543 people who wore a Fitbit and responded to the chatbot for more than 7 days on the same day were analyzed. Research participants tended to respond to sleep-related times on the hour or in 30-minute increments, and each participant responded within the range of 60-90 minutes from the value measured by the Fitbit. On average for all participants, the chat responses and the Fitbit data were similar within a difference of approximately 15 minutes. Regarding sleep onset, the participant response was 8 minutes and 39 seconds (SD 58 minutes) later than that of the Fitbit data, whereas with respect to sleep offset, the response was 5 minutes and 38 seconds (SD 57 minutes) earlier. The participants' actual sleep time (AST) indicated in the chat was similar to that obtained by subtracting the WASO from the TST measured by the Fitbit. The AST was 13 minutes and 39 seconds (SD 87 minutes) longer than the time WASO was subtracted from the Fitbit TST. On days when the participants reported good sleep, they responded 19 (SD 90) minutes longer on the AST than the Fitbit data. However, for each sleep event, the probability that the participant's AST was within ±30 and ±60 minutes of the Fitbit TST-WASO was 50.7% and 74.3%, respectively.

CONCLUSIONS

The chatbot sleep response and Fitbit measured time were similar on average and the study participants had a slight tendency to perceive a relatively long sleep time if the quality of sleep was self-reported as good. However, on a participant-by-participant basis, it was difficult to predict participants' sleep duration responses with Fitbit data. Individual variations in sleep time perception significantly affect patient responses related to sleep, revealing the limitations of objective measures obtained through wearable devices.

rTMS targeted to the secondary somatosensory cortex influences sleep in CRPS patients, as measured with the OURA ring

INTRODUCTION

Chronic pain associates with various sleep problems. Patients with complex regional pain syndrome (CRPS) often report impaired sleep, but objective measurements of sleep in CRPS patients are scarce. Neuromodulation with repetitive transcranial magnetic stimulation (rTMS) can alleviate pain and improve sleep. Secondary somatosensory cortex (S2) is a possible rTMS target for the treatment of chronic pain, but the effect of S2-targeted rTMS on sleep is unknown.

METHODS

This randomized, sham-controlled trial assessed the effect of S2-targeted rTMS on sleep in patients with CRPS. Patients (n = 31) received either S2-targeted rTMS (10 Hz) or sham stimulation for 3 weeks. The effect of treatment on sleep was assessed with validated questionnaires, with a sleep and pain diary, and with a consumer-grade sleep tracker, the Oura ring. In addition to an ordinary univariate analysis of the results, we conducted multivariate testing of the Oura data using linear discriminant analysis (LDA).

RESULTS

S2-targeted rTMS decreased sleep restlessness that significantly differed between the rTMS and sham stimulation patient groups (p = .028). In the multivariate analysis of the Oura data, LDA classification accuracy to separate the rTMS and sham groups exceeded 95% confidence level in four out of the seven tested models. In the subjective evaluation of sleep, the effect of rTMS and sham did not differ.

CONCLUSION

S2-targeted rTMS influenced sleep in patients with CRPS. Improved sleep may enhance CRPS symptom alleviation and be of clinical importance. A univariate analysis could separate the rTMS and sham treatments. The multivariate analysis revealed that including multiple sleep-related parameters can be beneficial when analyzing rTMS effects on sleep. As sleep is related both to pain and quality of life, and sleep rTMS can be directly affected by rTMS, objective monitoring of sleep in various future rTMS trials could be fruitful.

Performance of an open machine learning model to classify sleep/wake from actigraphy across ∼24-hour intervals without knowledge of rest timing

GOAL AND AIMS

Commonly used actigraphy algorithms are designed to operate within a known in-bed interval. However, in free-living scenarios this interval is often unknown. We trained and evaluated a sleep/wake classifier that operates on actigraphy over ∼24-hour intervals, without knowledge of in-bed timing.

FOCUS TECHNOLOGY

Actigraphy counts from ActiWatch Spectrum devices.

REFERENCE TECHNOLOGY

Sleep staging derived from polysomnography, supplemented by observation of wakefulness outside of the staged interval. Classifications from the Oakley actigraphy algorithm were additionally used as performance reference.

SAMPLE

Adults, sleeping in either a home or laboratory environment.

DESIGN

Machine learning was used to train and evaluate a sleep/wake classifier in a supervised learning paradigm. The classifier is a temporal convolutional network, a form of deep neural network.

CORE ANALYTICS

Performance was evaluated across ∼24 hours, and additionally restricted to only in-bed intervals, both in terms of epoch-by-epoch performance, and the discrepancy of summary statistics within the intervals.

ADDITIONAL ANALYTICS AND EXPLORATORY ANALYSES

Performance of the trained model applied to the Multi-Ethnic Study of Atherosclerosis dataset.

CORE OUTCOMES

Over ∼24 hours, the temporal convolutional network classifier produced the same or better performance as the Oakley classifier on all measures tested. When restricting analysis to the in-bed interval, the temporal convolutional network remained favorable on several metrics.

IMPORTANT SUPPLEMENTAL OUTCOMES

Performance decreased on the Multi-Ethnic Study of Atherosclerosis dataset, especially when restricting analysis to the in-bed interval.

CORE CONCLUSION

A classifier using data labeled over ∼24-hour intervals allows for the continuous classification of sleep/wake without knowledge of in-bed intervals. Further development should focus on improving generalization performance.

Monitoring Resistance Training in Real Time with Wearable Technology: Current Applications and Future Directions

Resistance training is an exercise modality that involves using weights or resistance to strengthen and tone muscles. It has become popular in recent years, with numerous people including it in their fitness routines to ameliorate their strength, muscle mass, and overall health. Still, resistance training can be complex, requiring careful planning and execution to avoid injury and achieve satisfactory results. Wearable technology has emerged as a promising tool for resistance training, as it allows monitoring and adjusting training programs in real time. Several wearable devices are currently available, such as smart watches, fitness trackers, and other sensors that can yield detailed physiological and biomechanical information. In resistance training research, this information can be used to assess the effectiveness of training programs and identify areas for improvement. Wearable technology has the potential to revolutionize resistance training research, providing new insights and opportunities for developing optimized training programs. This review examines the types of wearables commonly used in resistance training research, their applications in monitoring and optimizing training programs, and the potential limitations and challenges associated with their use. Finally, it discusses future research directions, including the development of advanced wearable technologies and the integration of artificial intelligence in resistance training research.

A 2022 Survey of Commercially Available Smartphone Apps for Sleep: Most Enhance Sleep

Commercially available smartphone apps represent an ever-evolving and fast-growing market. Our review systematically surveyed currently available commercial sleep smartphone apps to provide details to inform both providers and patients alike, in addition to the healthy consumer market. Most current sleep apps offer a free version and are designed to be used while awake, prior to sleep, and focus on the enhancement of sleep, rather than measurement, by targeting sleep latency using auditory stimuli. Sleep apps could be considered a possible strategy for patients and consumers to improve their sleep, although further validation of specific apps is recommended.

Consumer Wearable Sleep Trackers: Are They Ready for Clinical Use?

As the importance of good sleep continues to gain public recognition, the market for sleep-monitoring devices continues to grow. Modern technology has shifted from simple sleep tracking to a more granular sleep health assessment. We examine the available functionalities of consumer wearable sleep trackers (CWSTs) and how they perform in healthy individuals and disease states. Additionally, the continuum of sleep technology from consumer-grade to medical-grade is detailed. As this trend invariably grows, we urge professional societies to develop guidelines encompassing the practical clinical use of CWSTs and how best to incorporate them into patient care plans.

Dawn of a New Dawn: Advances in Sleep Health to Optimize Performance

Optimal sleep health is a critical component to high-level performance. In populations such as the military, public service (eg, firefighters), and health care, achieving optimal sleep health is difficult and subsequently deficiencies in sleep health may lead to performance decrements. However, advances in sleep monitoring technologies and mitigation strategies for poor sleep health show promise for further ecological scientific investigation within these populations. The current review briefly outlines the relationship between sleep health and performance as well as current advances in behavioral and technological approaches to improving sleep health for performance.

Applying machine learning to consumer wearable data for the early detection of complications after pediatric appendectomy

When children are discharged from the hospital after surgery, their caregivers often rely on subjective assessments (e.g., appetite, fatigue) to monitor postoperative recovery as objective assessment tools are scarce at home. Such imprecise and one-dimensional evaluations can result in unwarranted emergency department visits or delayed care. To address this gap in postoperative monitoring, we evaluated the ability of a consumer-grade wearable device, Fitbit, which records multimodal data about daily physical activity, heart rate, and sleep, in detecting abnormal recovery early in children recovering after appendectomy. One hundred and sixty-two children, ages 3-17 years old, who underwent an appendectomy (86 complicated and 76 simple cases of appendicitis) wore a Fitbit device on their wrist for 21 days postoperatively. Abnormal recovery events (i.e., abnormal symptoms or confirmed postoperative complications) that arose during this period were gathered from medical records and patient reports. Fitbit-derived measures, as well as demographic and clinical characteristics, were used to train machine learning models to retrospectively detect abnormal recovery in the two days leading up to the event for patients with complicated and simple appendicitis. A balanced random forest classifier accurately detected 83% of these abnormal recovery days in complicated appendicitis and 70% of abnormal recovery days in simple appendicitis prior to the true report of a symptom/complication. These results support the development of machine learning algorithms to predict onset of abnormal symptoms and complications in children undergoing surgery, and the use of consumer wearables as monitoring tools for early detection of postoperative events.

Clinical Evaluation of the Sleepy and Sleepless Patient

OBJECTIVE

This article addresses the approach to the evaluation of patients who present to a neurologist with excessive daytime sleepiness or difficulty sleeping.

LATEST DEVELOPMENTS

Greater emphasis on the importance of sleep reflects the growing scientific understanding that sleep is critical to overall health and well-being. Consumer sleep technologies, which measure parameters related to sleep, may provide insight into an individual's sleep-related symptoms and tendencies and have a role in patient-centered sleep evaluation when used within an appropriate clinical context.

ESSENTIAL POINTS

A thorough review of a patient's history and physical examination findings are important components of the assessment and management of their sleep-related symptoms. An understanding of how the clinical context relates to the categorization of sleep disorders can impact a patient's symptoms, comorbid neurologic disorders, and overall well-being. Many neurologic conditions are strongly associated with sleep disturbance, risk factors for the development of a sleep disorder, or both. Therefore, it is critical for neurologists to be familiar and comfortable with taking a focused sleep history. Modalities such as in-laboratory polysomnography, home sleep apnea testing, multiple sleep latency testing, and actigraphy, as well as contextualized and prudent use of data obtained from consumer sleep technologies, can be helpful in appropriately selected patients. Mindful integration of these objective data facilitates the diagnosis and management of sleep disorders.

Belun Ring (Belun Sleep System BLS-100): Deep learning-facilitated wearable enables obstructive sleep apnea detection, apnea severity categorization, and sleep stage classification in patients suspected of obstructive sleep apnea

GOAL AND AIMS

Our objective was to evaluate the performance of Belun Ring with second-generation deep learning algorithms in obstructive sleep apnea (OSA) detection, OSA severity categorization, and sleep stage classification.

FOCUS TECHNOLOGY

Belun Ring with second-generation deep learning algorithms REFERENCE TECHNOLOGY: In-lab polysomnography (PSG) SAMPLE: Eighty-four subjects (M: F = 1:1) referred for an overnight sleep study were eligible. Of these, 26% had PSG-AHI<5; 24% had PSG-AHI 5-15; 23% had PSG-AHI 15-30; 27% had PSG-AHI ≥ 30.

DESIGN

Rigorous performance evaluation by comparing Belun Ring to concurrent in-lab PSG using the 4% rule.

CORE ANALYTICS

Pearson's correlation coefficient, Student's paired t-test, diagnostic accuracy, sensitivity, specificity, positive predictive value, negative predictive value, positive likelihood ratio, negative likelihood ratio, Cohen's kappa coefficient (kappa), Bland-Altman plots with bias and limits of agreement, receiver operating characteristics curves with area under the curve, and confusion matrix.

CORE OUTCOMES

The accuracy, sensitivity, specificity, and kappa in categorizing AHI ≥ 5 were 0.85, 0.92, 0.64, and 0.58, respectively. The accuracy, sensitivity, specificity, and Kappa in categorizing AHI ≥ 15 were 0.89, 0.91, 0.88, and 0.79, respectively. The accuracy, sensitivity, specificity, and Kappa in categorizing AHI ≥ 30 were 0.91, 0.83, 0.93, and 0.76, respectively. BSP2 also achieved an accuracy of 0.88 in detecting wake, 0.82 in detecting NREM, and 0.90 in detecting REM sleep.

CORE CONCLUSION

Belun Ring with second-generation algorithms detected OSA with good accuracy and demonstrated a moderate-to-substantial agreement in categorizing OSA severity and classifying sleep stages.

Apple Watch Sleep and Physiological Tracking Compared to Clinically Validated Actigraphy, Ballistocardiography and Polysomnography

This paper investigates the performance of the latest Apple Watch (Series 8, released September 2022) in comparison with research grade devices. The Apple Watch was compared to wrist worn actigraphy, non-contact ballistocardiography (BCG) placed in the bed and evaluated with polysomnography (PSG) as a reference system. Sleep analysis and individual cardiorespiratory parameters were measured from the Apple Watch. The Apple Watch performed well for identifying sleep-wake states but had difficulty identifying the sleep stages compared to the reference PSG system. Physiological parameters obtained from the Apple Watch compared well with measurements of the other devices in the study.Clinical Relevance- Consumer devices are readily available and inexpensive compared to clinical devices. A consumer device that can provide accurate physiological data equivalent to a clinical device would let researchers and clinicians collect data without the intrusive nature of a clinical device.

Knowledge Discovery in Ubiquitous and Personal Sleep Tracking: Scoping Review

BACKGROUND

Over the past few decades, there has been a rapid increase in the number of wearable sleep trackers and mobile apps in the consumer market. Consumer sleep tracking technologies allow users to track sleep quality in naturalistic environments. In addition to tracking sleep per se, some sleep tracking technologies also support users in collecting information on their daily habits and sleep environments and reflecting on how those factors may contribute to sleep quality. However, the relationship between sleep and contextual factors may be too complex to be identified through visual inspection and reflection. Advanced analytical methods are needed to discover new insights into the rapidly growing volume of personal sleep tracking data.

OBJECTIVE

This review aimed to summarize and analyze the existing literature that applies formal analytical methods to discover insights in the context of personal informatics. Guided by the problem-constraints-system framework for literature review in computer science, we framed 4 main questions regarding general research trends, sleep quality metrics, contextual factors considered, knowledge discovery methods, significant findings, challenges, and opportunities of the interested topic.

METHODS

Web of Science, Scopus, ACM Digital Library, IEEE Xplore, ScienceDirect, Springer, Fitbit Research Library, and Fitabase were searched to identify publications that met the inclusion criteria. After full-text screening, 14 publications were included.

RESULTS

The research on knowledge discovery in sleep tracking is limited. More than half of the studies (8/14, 57%) were conducted in the United States, followed by Japan (3/14, 21%). Only a few of the publications (5/14, 36%) were journal articles, whereas the remaining were conference proceeding papers. The most used sleep metrics were subjective sleep quality (4/14, 29%), sleep efficiency (4/14, 29%), sleep onset latency (4/14, 29%), and time at lights off (3/14, 21%). Ratio parameters such as deep sleep ratio and rapid eye movement ratio were not used in any of the reviewed studies. A dominant number of the studies applied simple correlation analysis (3/14, 21%), regression analysis (3/14, 21%), and statistical tests or inferences (3/14, 21%) to discover the links between sleep and other aspects of life. Only a few studies used machine learning and data mining for sleep quality prediction (1/14, 7%) or anomaly detection (2/14, 14%). Exercise, digital device use, caffeine and alcohol consumption, places visited before sleep, and sleep environments were important contextual factors substantially correlated to various dimensions of sleep quality.

CONCLUSIONS

This scoping review shows that knowledge discovery methods have great potential for extracting hidden insights from a flux of self-tracking data and are considered more effective than simple visual inspection. Future research should address the challenges related to collecting high-quality data, extracting hidden knowledge from data while accommodating within-individual and between-individual variations, and translating the discovered knowledge into actionable insights.

Social dimensions impact individual sleep quantity and quality

While sleep positively impacts well-being, health, and productivity, the effects of societal factors on sleep remain underexplored. Here we analyze the sleep of 30,082 individuals across 11 countries using 52 million activity records from wearable devices. Our data are consistent with past studies of gender and age-associated sleep characteristics. However, our analysis of wearable device data uncovers differences in recorded vs. self-reported bedtime and sleep duration. The dataset allowed us to study how country-specific metrics such as GDP and cultural indices relate to sleep in groups and individuals. Our analysis indicates that diverse sleep metrics can be represented by two dimensions: sleep quantity and quality. We find that 55% of the variation in sleep quality, and 63% in sleep quantity, are explained by societal factors. Within a societal boundary, individual sleep experience was modified by factors like exercise. Increased exercise or daily steps were associated with better sleep quality (for example, faster sleep onset and less time awake in bed), especially in countries like the U.S. and Finland. Understanding how social norms relate to sleep will help create strategies and policies that enhance the positive impacts of sleep on health, such as productivity and well-being.

AI-Driven sleep staging from actigraphy and heart rate

Sleep is an important indicator of a person's health, and its accurate and cost-effective quantification is of great value in healthcare. The gold standard for sleep assessment and the clinical diagnosis of sleep disorders is polysomnography (PSG). However, PSG requires an overnight clinic visit and trained technicians to score the obtained multimodality data. Wrist-worn consumer devices, such as smartwatches, are a promising alternative to PSG because of their small form factor, continuous monitoring capability, and popularity. Unlike PSG, however, wearables-derived data are noisier and far less information-rich because of the fewer number of modalities and less accurate measurements due to their small form factor. Given these challenges, most consumer devices perform two-stage (i.e., sleep-wake) classification, which is inadequate for deep insights into a person's sleep health. The challenging multi-class (three, four, or five-class) staging of sleep using data from wrist-worn wearables remains unresolved. The difference in the data quality between consumer-grade wearables and lab-grade clinical equipment is the motivation behind this study. In this paper, we present an artificial intelligence (AI) technique termed sequence-to-sequence LSTM for automated mobile sleep staging (SLAMSS), which can perform three-class (wake, NREM, REM) and four-class (wake, light, deep, REM) sleep classification from activity (i.e., wrist-accelerometry-derived locomotion) and two coarse heart rate measures-both of which can be reliably obtained from a consumer-grade wrist-wearable device. Our method relies on raw time-series datasets and obviates the need for manual feature selection. We validated our model using actigraphy and coarse heart rate data from two independent study populations: the Multi-Ethnic Study of Atherosclerosis (MESA; N = 808) cohort and the Osteoporotic Fractures in Men (MrOS; N = 817) cohort. SLAMSS achieves an overall accuracy of 79%, weighted F1 score of 0.80, 77% sensitivity, and 89% specificity for three-class sleep staging and an overall accuracy of 70-72%, weighted F1 score of 0.72-0.73, 64-66% sensitivity, and 89-90% specificity for four-class sleep staging in the MESA cohort. It yielded an overall accuracy of 77%, weighted F1 score of 0.77, 74% sensitivity, and 88% specificity for three-class sleep staging and an overall accuracy of 68-69%, weighted F1 score of 0.68-0.69, 60-63% sensitivity, and 88-89% specificity for four-class sleep staging in the MrOS cohort. These results were achieved with feature-poor inputs with a low temporal resolution. In addition, we extended our three-class staging model to an unrelated Apple Watch dataset. Importantly, SLAMSS predicts the duration of each sleep stage with high accuracy. This is especially significant for four-class sleep staging, where deep sleep is severely underrepresented. We show that, by appropriately choosing the loss function to address the inherent class imbalance, our method can accurately estimate deep sleep time (SLAMSS/MESA: 0.61±0.69 hours, PSG/MESA ground truth: 0.60±0.60 hours; SLAMSS/MrOS: 0.53±0.66 hours, PSG/MrOS ground truth: 0.55±0.57 hours;). Deep sleep quality and quantity are vital metrics and early indicators for a number of diseases. Our method, which enables accurate deep sleep estimation from wearables-derived data, is therefore promising for a variety of clinical applications requiring long-term deep sleep monitoring.

Stellate Ganglion Block Improves Postoperative Sleep Quality and Analgesia in Patients with Breast Cancer: A Randomized Controlled Trial

INTRODUCTION

Postoperative impaired sleep quality and pain are associated with adverse outcomes. Stellate ganglion block (SGB) has shown promising results in enhancing sleep quality and alleviating neuropathic pain. This study aimed to investigate the effects of ultrasound-guided SGB on postoperative sleep quality and pain in patients undergoing breast cancer surgery.

METHODS

This study is a parallel-group randomized controlled clinical trial with two groups: SGB and control. Fifty female patients undergoing breast cancer surgery were randomized in a 1:1 ratio to receive preoperative ultrasound-guided single-injection SGB (SGB group) or just an ultrasound scan (control group). All participants were blinded to the group assignment. The primary outcome was postoperative sleep quality, assessed by the St. Mary's Hospital Sleep Questionnaire and actigraphy 2 days postoperatively. The secondary outcome was postoperative pain, measured by the visual analog scale.

RESULTS

A total of 48 patients completed the study, with 23 patients in the control group and 25 in the SGB group. The postoperative St. Mary's Hospital Sleep Questionnaire scores were significantly higher in the SGB group than in the control group on 1 day postoperative (30.88 ± 2.44 versus 27.35 ± 4.12 points, P = 0.001). The SGB also increased the total sleep time and sleep efficiency (main actigraphy indicators) during the first two postoperative nights. Compared with the control group, preoperative SGB reduced postoperative pain and the incidence of breast cancer-related lymphedema (20% versus 52.2%, P = 0.02, odds ratio 0.229, 95% confidence interval 0.064-0.821). There were no adverse events related to SGB.

CONCLUSION

Preoperative ultrasound-guided SGB improves postoperative sleep quality and analgesia in patients undergoing breast cancer surgery. SGB may be a safe and practical treatment to enhance the postoperative quality of life in patients with breast cancer.

TRIAL REGISTRATION

The study was registered in the Chinese Clinical Trial Registry (ChiCTR2100046620, principal investigator: Kai Zeng, date of registration: 23 May 2021).

The past, present, and future of sleep quality assessment and monitoring

Sleep quality is considered to be an individual's self-satisfaction with all aspects of the sleep experience. Good sleep not only improves a person's physical, mental and daily functional health, but also improves the quality-of-life level to some extent. In contrast, chronic sleep deprivation can increase the risk of diseases such as cardiovascular diseases, metabolic dysfunction and cognitive and emotional dysfunction, and can even lead to increased mortality. The scientific evaluation and monitoring of sleep quality is an important prerequisite for safeguarding and promoting the physiological health of the body. Therefore, we have compiled and reviewed the existing methods and emerging technologies commonly used for subjective and objective evaluation and monitoring of sleep quality, and found that subjective sleep evaluation is suitable for clinical screening and large-scale studies, while objective evaluation results are more intuitive and scientific, and in the comprehensive evaluation of sleep, if we want to get more scientific monitoring results, we should combine subjective and objective monitoring and dynamic monitoring.

The long-term and short-term effects of ambient air pollutants on sleep characteristics in the Chinese population: big data analysis from real world by sleep records of consumer wearable devices

Several studies on long-term air pollution exposure and sleep have reported inconsistent results. Large-scale studies on short-term air pollution exposures and sleep have not been conducted. We investigated the associations of long- and short-term exposure to ambient air pollutants with sleep in a Chinese population based on over 1 million nights of sleep data from consumer wearable devices. Air pollution data including particulate matter (PM_2.5, PM₁₀), nitrogen dioxide (NO₂), sulfur dioxide (SO₂), carbon monoxide (CO), and ozone (O₃) were collected from the Ministry of Ecology and Environment. Short-term exposure was defined as a moving average of the exposure level for different lag days from Lag0 to Lag0-6. A 365-day moving average of air pollution was regarded as long-term exposure. Sleep data were recorded using wearable devices from 2017 to 2019. The mixed-effects model was used to evaluate the associations. We observed that sleep parameters were associated with long-term exposure to all air pollutants. Higher levels of air pollutant concentrations were associated with longer total sleep and light sleep duration, shorter deep sleep duration, and decreases in wake after sleep onset (WASO), with stronger associations of exposures to NO₂ and CO [a 1-interquartile range (IQR) increased NO₂ (10.3 μg/m³) was associated with 8.7 min (95% CI: 8.08 to 9.32) longer sleep duration, a 1-IQR increased CO (0.3 mg/m³) was associated with 5.0 min (95% CI: - 5.13 to - 4.89) shorter deep sleep duration, 7.7 min (95% CI: 7.46 to 7.85) longer light sleep duration, and 0.5% (95% CI: - 0.5 to - 0.4%) lower proportion of WASO duration to total sleep]. The cumulative effect of short-term exposure on Lag0-6 is similar to long-term exposure but relatively less. Subgroup analyses indicated generally greater effects on individuals who were female, younger (< 45 years), slept longer (≥ 7 h), and during cold seasons, but the pattern of effects was mixed. We supplemented two additional types of stratified analyses to reduce repeated measures of outcomes and exposures while accounting for individual variation. The results were consistent with the overall results, proving the robustness of the overall results. In summary, both short- and long-term exposure to air pollution affect sleep, and the effects are comparable. Although people tend to have prolonged total sleep duration with increasing air pollutant concentrations, their sleep quality might remain poor because of the reduction in deep sleep.

A Wrinkle in Measuring Time Use for Cognitive Health: How should We Measure Physical Activity, Sedentary Behaviour and Sleep?

One new case of dementia is detected every 4 seconds and no effective drug therapy exists. Effective behavioural strategies to promote healthy cognitive ageing are thus essential. Three behaviours related to cognitive health which we all engage in daily are physical activity, sedentary behaviour and sleep. These time-use activity behaviours are linked to cognitive health in a complex and dynamic relationship not yet fully elucidated. Understanding how each of these behaviours is related to each other and cognitive health will help determine the most practical and effective lifestyle strategies for promoting healthy cognitive ageing. In this review, we discuss methods and analytical approaches to best investigate how these time-use activity behaviours are related to cognitive health. We highlight four key recommendations for examining these relationships such that researchers should include measures which (1) are psychometrically appropriate; (2) can specifically answer the research question; (3) include objective and subjective estimates of the behaviour and (4) choose an analytical method for modelling the relationships of time-use activity behaviours with cognitive health which is appropriate for their research question.

Validation of Oura ring energy expenditure and steps in laboratory and free-living

BACKGROUND

Commercial activity trackers are increasingly used in research and compared with research-based accelerometers are often less intrusive, cheaper, with improved storage and battery capacity, although typically less validated. The present study aimed to determine the validity of Oura Ring step-count and energy expenditure (EE) in both laboratory and free-living.

METHODS

Oura Ring EE was compared against indirect calorimetry in the laboratory, followed by a 14-day free-living study with 32 participants wearing an Oura Ring and reference monitors (three accelerometers positioned at hip, thigh, and wrist, and pedometer) to evaluate Oura EE variables and step count.

RESULTS

Strong correlations were shown for Oura versus indirect calorimetry in the laboratory (r = 0.93), and versus reference monitors for all variables in free-living (r ≥ 0.76). Significant (p < 0.05) mean differences for Oura versus reference methods were found for laboratory measured sitting (- 0.12 ± 0.28 MET), standing (- 0.27 ± 0.33 MET), fast walk (- 0.82 ± 1.92 MET) and very fast run (- 3.49 ± 3.94 MET), and for free-living step-count (2124 ± 4256 steps) and EE variables (MET: - 0.34-0.26; TEE: 362-494 kcal; AEE: - 487-259 kcal). In the laboratory, Oura tended to underestimate EE with increasing discrepancy as intensity increased. The combined activities and slow running in the laboratory, and all MET placements, TEE hip and wrist, and step count in free-living had acceptable measurement errors (< 10% MAPE), whereas the remaining free-living variables showed close to (≤13.2%) acceptable limits.

CONCLUSION

This is the first study investigating the validity of Oura Ring EE against gold standard methods. Oura successfully identified major changes between activities and/or intensities but was less responsive to detailed deviations within activities. In free-living, Oura step-count and EE variables tightly correlated with reference monitors, though with systemic over- or underestimations indicating somewhat low intra-individual validity of the ring versus the reference monitors. However, the correlations between the devices were high, suggesting that the Oura can detect differences at group-level for active and total energy expenditure, as well as step count.

Pyjamas, Polysomnography and Professional Athletes: The Role of Sleep Tracking Technology in Sport

Technological advances in sleep monitoring have seen an explosion of devices used to gather important sleep metrics. These devices range from instrumented 'smart pyjamas' through to at-home polysomnography devices. Alongside these developments in sleep technologies, there have been concomitant increases in sleep monitoring in athletic populations, both in the research and in practical settings. The increase in sleep monitoring in sport is likely due to the increased knowledge of the importance of sleep in the recovery process and performance of an athlete, as well as the well-reported challenges that athletes can face with their sleep. This narrative review will discuss: (1) the importance of sleep to athletes; (2) the various wearable tools and technologies being used to monitor sleep in the sport setting; (3) the role that sleep tracking devices may play in gathering information about sleep; (4) the reliability and validity of sleep tracking devices; (5) the limitations and cautions associated with sleep trackers; and, (6) the use of sleep trackers to guide behaviour change in athletes. We also provide some practical recommendations for practitioners working with athletes to ensure that the selection of such devices and technology will meet the goals and requirements of the athlete.

Investigating the effectiveness of electronically delivered cognitive behavioural therapy (e-CBTi) compared to pharmaceutical interventions in treating insomnia: Protocol for a randomized controlled trial

BACKGROUND

Insomnia is one of the most prevalent sleep disorders characterized by an inability to fall or stay asleep. Available treatments include pharmacotherapy and cognitive behavioural therapy for insomnia (CBTi). Although CBTi is the first-line treatment, it has limited availability. Therapist-guided electronic delivery of CBT for insomnia (e-CBTi) offers scalable solutions to enhance access to CBTi. While e-CBTi produces comparable outcomes to in-person CBTi, there is a lack of comparison to active pharmacotherapies. Therefore, direct comparisons between e-CBTi and trazodone, one of the most frequently prescribed medications for insomnia, is essential in establishing the effectiveness of this novel digital therapy in the health care system.

OBJECTIVE

The aim of this study is to compare the effectiveness of a therapist-guided electronically-delivered cognitive behavioural therapy (e-CBTi) program to trazodone in patients with insomnia.

METHODS

Patients (n = 60) will be randomly assigned to two groups: treatment as usual (TAU) + trazodone and TAU + e-CBTi for seven weeks. Each weekly sleep module will be delivered through the Online Psychotherapy Tool (OPTT), a secure, online mental health care delivery platform. Changes in insomnia symptoms will be evaluated throughout the study using clinically validated symptomatology questionnaires, Fitbits, and other behavioural variables.

RESULTS

Participant recruitment began in November 2021. To date, 18 participants have been recruited. Data collection is expected to conclude by December 2022 and analyses are expected to be completed by January 2023.

CONCLUSIONS

This comparative study will improve our understanding of the efficacy of therapist-guided e-CBTi in managing insomnia. These findings can be used to develop more accessible and effective treatment options and influence clinical practices for insomnia to further expand mental health care capacity in this population.

TRIAL REGISTRATION

ClinicalTrials.gov (NCT05125146).

Comparison of Oura Smart Ring Against ActiGraph Accelerometer for Measurement of Physical Activity and Sedentary Time in a Free-Living Context

Smart rings, such as the Oura ring, might have potential in health monitoring. To be able to identify optimal devices for healthcare settings, validity studies are needed. The aim of this study was to compare the Oura smart ring estimates of steps and sedentary time with data from the ActiGraph accelerometer in a free-living context. A cross-sectional observational study design was used. A convenience sample of healthy adults (n = 42) participated in the study and wore an Oura smart ring and an ActiGraph accelerometer on the non-dominant hand continuously for 1 week. The participants completed a background questionnaire and filled out a daily log about their sleeping times and times when they did not wear the devices. The median age of the participants (n = 42) was 32 years (range, 18-46 years). In total, 191 (61% of the potential) days were compared. The Oura ring overestimated the step counts compared with the ActiGraph. The mean difference was 1416 steps (95% confidence interval, 739-2093 steps). Daily sedentary time was also overestimated by the ring; the mean difference was 17 minutes (95% confidence interval, -2 to 37 minutes). The use of the ring in nursing interventions needs to be considered.

"Leave your smartphone out of bed": quantitative analysis of smartphone use effect on sleep quality

Smartphones have become an integral part of people's everyday lives. Smartphones are used across all household locations, including in the bed at night. Smartphone screens and other displays emit blue light, and exposure to blue light can affect one's sleep quality. Thus, smartphone use prior to bedtime could disrupt the quality of one's sleep, but research lacks quantitative studies on how smartphone use can influence sleep. This study combines smartphone application use data from 75 participants with sleep data collected by a wearable ring. On average, the participants used their smartphones in bed for 322.8 s (5 min and 22.8 s), with an IQR of 43.7-456. Participants spent an average of 42% of their time in bed using their smartphones (IQR of 5.87-55.5%). Our findings indicate that smartphone use in bed has significant adverse effects on sleep latency, awake time, average heart rate, and HR variability. We also find that smartphone use does not decrease sleep quality when used outside of bed. Our results indicate that intense smartphone use alone does not negatively affect well-being. Since all smartphone users do not use their phones in the same way, extending the investigation to different smartphone use types might yield more information than general smartphone use. In conclusion, this paper presents the first investigation of the association between smartphone application use logs and detailed sleep metrics. Our work also validates previous research results and highlights emerging future work.

Detecting Sleep and Nonwear in 24-h Wrist Accelerometer Data from the National Health and Nutrition Examination Survey

INTRODUCTION

Estimating physical activity, sedentary behavior, and sleep from wrist-worn accelerometer data requires reliable detection of sensor nonwear and sensor wear during both sleep and wake.

PURPOSE

This study aimed to develop an algorithm that simultaneously identifies sensor wake-wear, sleep-wear, and nonwear in 24-h wrist accelerometer data collected with or without filtering.

METHODS

Using sensor data labeled with polysomnography ( n = 21) and directly observed wake-wear data ( n = 31) from healthy adults, and nonwear data from sensors left at various locations in a home ( n = 20), we developed an algorithm to detect nonwear, sleep-wear, and wake-wear for "idle sleep mode" (ISM) filtered data collected in the 2011-2014 National Health and Nutrition Examination Survey. The algorithm was then extended to process original raw data collected from devices without ISM filtering. Both algorithms were further validated using a polysomnography-based sleep and wake-wear data set ( n = 22) and diary-based wake-wear and nonwear labels from healthy adults ( n = 23). Classification performance (F1 scores) was compared with four alternative approaches.

RESULTS

The F1 score of the ISM-based algorithm on the training data set using leave-one-subject-out cross-validation was 0.95 ± 0.13. Validation on the two independent data sets yielded F1 scores of 0.84 ± 0.60 for the data set with sleep-wear and wake-wear and 0.94 ± 0.04 for the data set with wake-wear and nonwear. The F1 score when using original, raw data was 0.96 ± 0.08 for the training data sets and 0.86 ± 0.18 and 0.97 ± 0.04 for the two independent validation data sets. The algorithm performed comparably or better than the alternative approaches on the data sets.

CONCLUSIONS

A novel machine-learning algorithm was designed to recognize wake-wear, sleep-wear, and nonwear in 24-h wrist-worn accelerometer data that are applicable for ISM-filtered data or original raw data.

An Automated Algorithm for Determining Sleep Using Single-Channel Electroencephalography to Detect Delirium: A Prospective Observational Study in Intensive Care Units

The relationship between polysomnography-based objective sleep and delirium in the intensive care unit (ICU) is inconsistent across studies, suggesting limitations in manually determining the sleep stage of critically ill patients. We objectively measured 24-h sleep using a single-channel electroencephalogram (SleepScope [SS]) and an under-mattress sleep monitor (Nemuri SCAN [NSCAN]), both of which have independent algorithms that automatically determine sleep and wakefulness. Eighteen patients (median age, 68 years) admitted to the ICU after valvular surgery or coronary artery bypass grafting were included, and their sleep time was measured one day after extubation. The median total sleep times (TSTs) measured by SS (TST-SS) and NSCAN were 548 (48−1050) and 1024 (462−1257) min, respectively. Two patients with delirium during the 24-h sleep measurement had very short TST-SS of 48 and 125 min, and the percentage of daytime sleep accounted for >80% in both SS and NSCAN. This preliminary case series showed marked sleep deprivation and increased rates of daytime sleeping in ICU patients with delirium. Although data accuracy from under-mattress sleep monitors is contentious, automated algorithmic sleep/wakefulness determination using a single-channel electroencephalogram may be useful in detecting delirium in ICU patients and could even be superior to polysomnography.

A systematic review of deep learning methods for modeling electrocardiograms during sleep

Sleep is one of the most important human physiological activities and plays an essential role in human health. Polysomnography (PSG) is the gold standard for measuring sleep quality and disorders, but it is time-consuming, labor-intensive, and prone to errors. Current research has confirmed the correlations between sleep and the respiratory/circulatory system. Electrocardiography (ECG) is convenient to perform, and ECG data are rich in breathing information. Therefore, sleep research based on ECG data has become popular. Currently, deep learning (DL) methods have achieved promising results on predictive health care tasks using ECG signals. Therefore, in this review, we systematically identify recent research studies and analyze them from the perspectives of data, model, and task. We discuss the shortcomings, summarize the findings, and highlight the potential opportunities. For sleep-related tasks, many ECG-based DL methods produce more accurate results than traditional approaches by combining multiple signal features and model structures. Methods that are more interpretable, scalable, and transferable will become ubiquitous in the daily practice of medicine and ambient-assisted-living applications. This paper is the first systematic review of ECG-based DL methods for sleep tasks.

Monitoring Variables Influence on Random Forest Models to Forecast Injuries in Short-Track Speed Skating

Injuries limit the athletes' ability to participate fully in their training and competitive process. They are detrimental to performance, affecting the athletes psychologically while limiting physiological adaptations and long-term development. This study aims to present a framework for developing random forest classifier models, forecasting injuries in the upcoming 1 to 7 days, to assist the performance support staff in reducing injuries and maximizing performance within the Canadian National Female Short-Track Speed Skating Program. Forty different variables monitored daily over two seasons (2018-2019 and 2019-2020) were used to develop two sets of forecasting models. One includes only training load variables (TL), and a second (ALL) combines a wide array of monitored variables (neuromuscular function, heart rate variability, training load, psychological wellbeing, past injury type, and location). The sensitivity (ALL: 0.35 ± 0.19, TL: 0.23 ± 0.03), specificity (ALL: 0.81 ± 0.05, TL: 0.74 ± 0.03) and Matthews Correlation Coefficients (MCC) (ALL: 0.13 ± 0.05, TL: -0.02 ± 0.02) were computed. Paired T-test on the MCC revealed statistically significant (p < 0.01) and large positive effects (Cohen d > 1) for the ALL forecasting models' MCC over every forecasting window (1 to 7 days). These models were highly determined by the athletes' training completion, lower limb and trunk/lumbar injury history, as well as sFatigue, a training load marker. The TL forecasting models' MCC suggests they do not bring any added value to forecast injuries. Combining a wide array of monitored variables and quantifying the injury etiology conceptual components significantly improve the injury forecasting performance of random forest models. The ALL forecasting models' performances are promising, especially on one time windows of one or two days, with sensitivities and specificities being respectively above 0.5 and 0.7. They could add value to the decision-making process for the support staff in order to assist the Canadian National Female Team Short-Track Speed Skating program in reducing the number of incomplete training days, which could potentially increase performance. On longer forecasting time windows, ALL forecasting models' sensitivity and MCC decrease gradually. Further work is needed to determine if such models could be useful for forecasting injuries over three days or longer.

Stress Resilience Program for Health Care Professionals During a Pandemic: A Pilot Program

BACKGROUND

The COVID-19 pandemic has led to increased burnout and staff turnover for health care providers (HCPs). The purpose of this pilot study was to evaluate the safety and acceptability of a Stress Resilience Program (SRP) for reducing perceived stress and improving resilience among HCPs during a pandemic.

METHOD

Of the 12 HCPs expressing interest in the study, 10 were enrolled in this study. Participants attended three in-person visits (consent/screen, baseline, and end-of-study). The SRP consisted of education related to resilience enhancement and a breathing device (BreatherFit®) for combined respiratory muscle training (cRMT). Participants completed 4 weeks of cRMT and applied situational breathing strategies as needed. Outcomes measured were changes in stress (PSS-10), resilience (BRS), depression (PRIME-MD), and sleep (PSQI and Ōura Ring®).

FINDINGS

The majority of participants were male (60%) and White (60%) with an average age of 39.7 years. Changes from baseline to end-of-treatment indicated a positive trend with significant stress reduction (-3.2 ± 3.9, p = .028) and nonsignificant depression reduction (-0.5 ± 0.7, p = .05). Resilience was high at baseline and continued to stay high during the study with a nonsignificant increase at end-of-study (+0.07 ± 0.7, p = .77). No changes in overall sleep scores were noted. All participants agreed the study was worthwhile, 80% indicated they would repeat the experience, while 90% indicated they would recommend the study to others.

CONCLUSION/APPLICATION TO PRACTICE

Because of its size and portability, SRP is an easily applicable and promising option for reducing stress among HCPs during a high-stress period, such as a pandemic. Larger studies are needed.

Considerations for Conducting Bring Your Own “Device” (BYOD) Clinical Studies

Background

Digital health technologies are attracting attention as novel tools for data collection in clinical research. They present alternative methods compared to in-clinic data collection, which often yields snapshots of the participants' physiology, behavior, and function that may be prone to biases and artifacts, e.g., white coat hypertension, and not representative of the data in free-living conditions. Modern digital health technologies equipped with multi-modal sensors combine different data streams to derive comprehensive endpoints that are important to study participants and are clinically meaningful. Used for data collection in clinical trials, they can be deployed as provisioned products where technology is given at study start or in a bring your own “device” (BYOD) manner where participants use their technologies to generate study data.

Summary

The BYOD option has the potential to be more user-friendly, allowing participants to use technologies that they are familiar with, ensuring better participant compliance, and potentially reducing the bias that comes with introducing new technologies. However, this approach presents different technical, operational, regulatory, and ethical challenges to study teams. For example, BYOD data can be more heterogeneous, and recruiting historically underrepresented populations with limited access to technology and the internet can be challenging. Despite the rapid increase in digital health technologies for clinical and healthcare research, BYOD use in clinical trials is limited, and regulatory guidance is still evolving.

Key Messages

We offer considerations for academic researchers, drug developers, and patient advocacy organizations on the design and deployment of BYOD models in clinical research. These considerations address: (1) early identification and engagement with internal and external stakeholders; (2) study design including informed consent and recruitment strategies; (3) outcome, endpoint, and technology selection; (4) data management including compliance and data monitoring; (5) statistical considerations to meet regulatory requirements. We believe that this article acts as a primer, providing insights into study design and operational requirements to ensure the successful implementation of BYOD clinical studies.

Rigorous performance evaluation (previously, "validation") for informed use of new technologies for sleep health measurement

New sleep technologies have become pervasive in the consumer space, and are becoming highly common in research and clinical sleep settings. The rapid, widespread use of largely unregulated and unstandardized technology has enabled the quantification of many different facets of sleep health, driving scientific discovery. As sleep scientists, it is our responsibility to inform principles and practices for proper evaluation of any new technology used in the clinical and research settings, and by consumers. A current lack of standardized methods for evaluating technology performance challenges the rigor of our scientific methods for accurate representation of the sleep health facets of interest. This special article describes the rationale and priorities of an interdisciplinary effort for rigorous, standardized, and rapid performance evaluation (previously, "validation") of new sleep and sleep disorders related technologies of all kinds (eg, devices or algorithms), including an associated article template for a new initiative for publication in Sleep Health of empirical studies systematically evaluating the performance of new sleep technologies. A structured article type should streamline manuscript development and enable more rapid writing, review, and publication. The goal is to promote rapid and rigorous evaluation and dissemination of new sleep technology, to enhance sleep research integrity, and to standardize terminology used in Rigorous Performance Evaluation papers to prevent misinterpretation while facilitating comparisons across technologies.

An Overview of the Sensors for Heart Rate Monitoring Used in Extramural Applications

This work presents an overview of the main strategies that have been proposed for non-invasive monitoring of heart rate (HR) in extramural and home settings. We discuss three categories of sensing according to what physiological effect is used to measure the pulsatile activity of the heart, and we focus on an illustrative sensing modality for each of them. Therefore, electrocardiography, photoplethysmography, and mechanocardiography are presented as illustrative modalities to sense electrical activity, mechanical activity, and the peripheral effect of heart activity. In this paper, we describe the physical principles underlying the three categories and the characteristics of the different types of sensors that belong to each class, and we touch upon the most used software strategies that are currently adopted to effectively and reliably extract HR. In addition, we investigate the strengths and weaknesses of each category linked to the different applications in order to provide the reader with guidelines for selecting the most suitable solution according to the requirements and constraints of the application.

Detecting sleep outside the clinic using wearable heart rate devices

The adoption of multisensor wearables presents the opportunity of longitudinal monitoring of sleep in large populations. Personalized yet device-agnostic algorithms can sidestep laborious human annotations and objectify cross-cohort comparisons. We developed and tested a heart rate-based algorithm that captures inter- and intra-individual sleep differences in free-living conditions and does not require human input. We evaluated it on four study cohorts using different research- and consumer-grade devices for over 2000 nights. Recording periods included both 24 h free-living and conventional lab-based night-only data. We compared our optimized method against polysomnography, sleep diaries and sleep periods produced through a state-of-the-art acceleration based method. Against sleep diaries, the algorithm yielded a mean squared error of 0.04-0.06 and a total sleep time (TST) deviation of [Formula: see text]2.70 (± 5.74) and 12.80 (± 3.89) minutes, respectively. When evaluated with PSG lab studies, the MSE ranged between 0.06 and 0.11 yielding a time deviation between [Formula: see text]29.07 and [Formula: see text]55.04 minutes. These results showcase the value of this open-source, device-agnostic algorithm for the reliable inference of sleep in free-living conditions and in the absence of annotations.

Combining cardiac monitoring with actigraphy aids nocturnal arousal detection during ambulatory sleep assessment in insomnia

STUDY OBJECTIVES

The objective assessment of insomnia has remained difficult. Multisensory devices collecting heart rate (HR) and motion are regarded as the future of ambulatory sleep monitoring. Unfortunately, reports on altered average HR or heart rate variability (HRV) during sleep in insomnia are equivocal. Here, we evaluated whether the objective quantification of insomnia improves by assessing state-related changes in cardiac measures.

METHODS

We recorded electrocardiography, posture, and actigraphy in 33 people without sleep complaints and 158 patients with mild to severe insomnia over 4 d in their home environment. At the microscale, we investigated whether HR changed with proximity to gross (body) and small (wrist) movements at nighttime. At the macroscale, we calculated day-night differences in HR and HRV measures. For both timescales, we tested whether outcome measures were related to insomnia diagnosis and severity.

RESULTS

At the microscale, an increase in HR was often detectable already 60 s prior to as well as following a nocturnal chest, but not wrist, movement. This increase was slightly steeper in insomnia and was associated with insomnia severity, but future EEG recordings are necessary to elucidate whether these changes occur prior to or simultaneously with PSG-indicators of wakefulness. At the macroscale, we found an attenuated cardiac response to sleep in insomnia: patients consistently showed smaller day-night differences in HR and HRV.

CONCLUSIONS

Incorporating state-related changes in cardiac features in the ambulatory monitoring of sleep might provide a more sensitive biomarker of insomnia than the use of cardiac activity averages or actigraphy alone.

Performance Evaluation of a Smart Bed Technology against Polysomnography

The Sleep Number smart bed uses embedded ballistocardiography, together with network connectivity, signal processing, and machine learning, to detect heart rate (HR), breathing rate (BR), and sleep vs. wake states. This study evaluated the performance of the smart bed relative to polysomnography (PSG) in estimating epoch-by-epoch HR, BR, sleep vs. wake, mean overnight HR and BR, and summary sleep variables. Forty-five participants (aged 22–64 years; 55% women) slept one night on the smart bed with standard PSG. Smart bed data were compared to PSG by Bland–Altman analysis and Pearson correlation for epoch-by-epoch HR and epoch-by-epoch BR. Agreement in sleep vs. wake classification was quantified using Cohen’s kappa, ROC analysis, sensitivity, specificity, accuracy, and precision. Epoch-by-epoch HR and BR were highly correlated with PSG (HR: r = 0.81, |bias| = 0.23 beats/min; BR: r = 0.71, |bias| = 0.08 breaths/min), as were estimations of mean overnight HR and BR (HR: r = 0.94, |bias| = 0.15 beats/min; BR: r = 0.96, |bias| = 0.09 breaths/min). Calculated agreement for sleep vs. wake detection included kappa (prevalence and bias-adjusted) = 0.74 ± 0.11, AUC = 0.86, sensitivity = 0.94 ± 0.05, specificity = 0.48 ± 0.18, accuracy = 0.86 ± 0.11, and precision = 0.90 ± 0.06. For all-night summary variables, agreement was moderate to strong. Overall, the findings suggest that the Sleep Number smart bed may provide reliable metrics to unobtrusively characterize human sleep under real life-conditions.

Performance of Four Commercial Wearable Sleep-Tracking Devices Tested Under Unrestricted Conditions at Home in Healthy Young Adults

PURPOSE

Commercial wearable sleep-tracking devices are growing in popularity and in recent studies have performed well against gold standard sleep measurement techniques. However, most studies were conducted in controlled laboratory conditions. We therefore aimed to test the performance of devices under naturalistic unrestricted home sleep conditions.

PARTICIPANTS AND METHODS

Healthy young adults (n = 21; 12 women, 9 men; 29.0 ± 5.0 years, mean ± SD) slept at home under unrestricted conditions for 1 week using a set of commercial wearable sleep-tracking devices and completed daily sleep diaries. Devices included the Fatigue Science Readiband, Fitbit Inspire HR, Oura ring, and Polar Vantage V Titan. Participants also wore a research-grade actigraphy watch (Philips Respironics Actiwatch 2) for comparison. To assess performance, all devices were compared with a high performing mobile sleep electroencephalography headband device (Dreem 2). Analyses included epoch-by-epoch and sleep summary agreement comparisons.

RESULTS

Devices accurately tracked sleep-wake summary metrics (ie, time in bed, total sleep time, sleep efficiency, sleep latency, wake after sleep onset) on most nights but performed best on nights with higher sleep efficiency. Epoch-by-epoch sensitivity (for sleep) and specificity (for wake), respectively, were as follows: Actiwatch (0.95, 0.35), Fatigue Science (0.94, 0.40), Fitbit (0.93, 0.45), Oura (0.94, 0.41), and Polar (0.96, 0.35). Sleep stage-tracking performance was mixed, with high variability.

CONCLUSION

As in previous studies, all devices were better at detecting sleep than wake, and most devices compared favorably to actigraphy in wake detection. Devices performed best on nights with more consolidated sleep patterns. Unrestricted sleep TIB differences were accurately tracked on most nights. High variability in sleep stage-tracking performance suggests that these devices, in their current form, are still best utilized for tracking sleep-wake outcomes and not sleep stages. Most commercial wearables exhibited promising performance for tracking sleep-wake in real-world conditions, further supporting their consideration as an alternative to actigraphy.

Multi-Night at-Home Evaluation of Improved Sleep Detection and Classification with a Memory-Enhanced Consumer Sleep Tracker

PURPOSE

To evaluate the benefits of applying an improved sleep detection and staging algorithm on minimally processed multi-sensor wearable data collected from older generation hardware.

PATIENTS AND METHODS

58 healthy, East Asian adults aged 23-69 years (M = 37.10, SD = 13.03, 32 males), each underwent 3 nights of PSG at home, wearing 2^nd Generation Oura Rings equipped with additional memory to store raw data from accelerometer, infra-red photoplethysmography and temperature sensors. 2-stage and 4-stage sleep classifications using a new machine-learning algorithm (Gen3) trained on a diverse and independent dataset were compared to the existing consumer algorithm (Gen2) for whole-night and epoch-by-epoch metrics.

RESULTS

Gen 3 outperformed its predecessor with a mean (SD) accuracy of 92.6% (0.04), sensitivity of 94.9% (0.03), and specificity of 78.5% (0.11); corresponding to a 3%, 2.8% and 6.2% improvement from Gen2 across the three nights, with Cohen's d values >0.39, t values >2.69, and p values <0.01. Notably, Gen 3 showed robust performance comparable to PSG in its assessment of sleep latency, light sleep, rapid eye movement (REM), and wake after sleep onset (WASO) duration. Participants <40 years of age benefited more from the upgrade with less measurement bias for total sleep time (TST), WASO, light sleep and sleep efficiency compared to those ≥40 years. Males showed greater improvements on TST and REM sleep measurement bias compared to females, while females benefitted more for deep sleep measures compared to males.

CONCLUSION

These results affirm the benefits of applying machine learning and a diverse training dataset to improve sleep measurement of a consumer wearable device. Importantly, collecting raw data with appropriate hardware allows for future advancements in algorithm development or sleep physiology to be retrospectively applied to enhance the value of longitudinal sleep studies.